PACS: Prediction and analysis of cancer subtypes from multi-omics data based on a multi-head attention mechanism model

TL;DR

This paper introduces a supervised multi-head attention model (SMA) that effectively classifies cancer subtypes from multi-omics data, outperforming existing models in accuracy and robustness across various datasets.

Contribution

The study presents a novel attention-based model with feature sharing and deep fusion modules for improved multi-omics cancer subtype classification.

Findings

SMA achieves highest accuracy in multiple datasets

Outperforms AE, CNN, and GNN models

Effective learning of global and local features

Abstract

Due to the high heterogeneity and clinical characteristics of cancer, there are significant differences in multi-omic data and clinical characteristics among different cancer subtypes. Therefore, accurate classification of cancer subtypes can help doctors choose the most appropriate treatment options, improve treatment outcomes, and provide more accurate patient survival predictions. In this study, we propose a supervised multi-head attention mechanism model (SMA) to classify cancer subtypes successfully. The attention mechanism and feature sharing module of the SMA model can successfully learn the global and local feature information of multi-omics data. Second, it enriches the parameters of the model by deeply fusing multi-head attention encoders from Siamese through the fusion module. Validated by extensive experiments, the SMA model achieves the highest accuracy, F1 macroscopic, F1 weighted, and accurate classification of cancer subtypes in simulated, single-cell, and cancer multiomics datasets compared to AE, CNN, and GNN-based models. Therefore, we contribute to future research on multiomics data using our attention-based approach.